Fast active power regulation method of DPVs based on optimal dynamic droop coefficient

Abstract

The present invention relates to a DPVs fast active power regulation method based on an optimal dynamic droop coefficient, comprising: selecting adjustable capacity and response time as clustering features, applying the U‑k‑means algorithm to implement clustering division on DPVs; constructing a frequency deviation-optimal droop coefficient model considering regulation performance and network loss based on the divided DPVs clusters; and applying GAT to pre-fast solve the optimal droop coefficient regulation strategy under various frequency deviation conditions, ensuring the active response of the DPVs clusters to the optimal droop coefficient regulation when a frequency event occurs, and realizing fast regulation of the active power output of the DPVs according to the power-frequency relationship. The present invention has the advantages of accuracy and efficiency in realizing fast active power regulation based on the droop coefficient using massive DPVs.

Description

Technical Field

[0001] The invention relates to a DPVs fast active power regulation method based on an optimal dynamic droop coefficient, and belongs to the technical field of smart grids. Background Art

[0002] The deployment of renewable energy in the power system is the only way to achieve carbon neutrality. With the advantages of low maintenance cost, high energy conversion rate and long life, distributed photovoltaics (DPVs) have become the main component of renewable energy, and their penetration rate in the power grid continues to rise. Connected to the distribution network. On the one hand, massive DPVs replace traditional generators, resulting in insufficient frequency support capacity of the power system; on the other hand, DPVs based on inverter interaction have fast active power regulation response performance. Therefore, it is imperative to develop and utilize the fast active power regulation potential of massive distributed photovoltaics.

[0003] However, directly controlling massive and dispersed distributed resources will cause dimensionality disaster and huge computational complexity. To this end, the present invention introduces clustering technology to classify DPVs with similar characteristics into the same group, and then treats them as an entity to participate in the rapid active power regulation of the power system, which can greatly improve the computational efficiency. At the same time, more and more studies have realized that it is of great significance to realize the rapid active power regulation of distributed resources based on the droop coefficient strategy. However, there are few research and development studies on the droop coefficient regulation of DPVs at present, and the existing studies have ignored the influence of network current in the process of designing the droop coefficient, which not only leads to inaccurate response to the regulation instruction, but also increases the risk of voltage over-limit. In addition, the existing droop coefficient regulation strategy must be calculated by the control center every time a frequency event occurs before being issued to DPVs. Under the timeliness requirements of the rapid regulation service, when frequency events occur frequently, this instruction issuance process has extremely high requirements on communication resources, and the communication delay problem cannot be avoided. Moreover, such a response process is passive, which does not match the active response mechanism based on droop coefficient regulation. To make up for the above shortcomings, the present invention constructs a frequency deviation-optimal droop coefficient model to achieve accurate and reliable response to the regulation command from the perspective of power flow optimization. Taking into account the initiative and timeliness requirements of the rapid active power regulation response based on the droop coefficient, the present invention uses a graph attention network (GAT) that introduces an attention mechanism to aggregate neighbor information in the topological space according to its importance to quickly solve the droop coefficient optimization model under various frequency deviations in advance, and obtain the optimal droop coefficient adjustment strategy for distributed photovoltaics. Finally, the active power output regulation of DPVs is realized according to the power-frequency relationship. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method for actively regulating and controlling the active power of massive distributed photovoltaic aggregates based on the optimal dynamic droop coefficient. Taking into account that directly regulating massive distributed photovoltaics will lead to dimensionality disasters and severe computational burdens, clustering of distributed photovoltaics is achieved based on the Uk-means algorithm. At the same time, in order to accurately and safely meet the regulation instructions issued by the balancing mechanism, a frequency deviation-optimal droop coefficient model that takes into account the regulation performance and transmission loss is constructed from the perspective of power flow optimization, and the optimal droop coefficient adjustment strategy under various frequency deviation conditions is quickly calculated in advance through the GAT algorithm to ensure active response when frequency events occur.

[0005] To achieve the above object, the present invention adopts the following technical solution: a DPVs fast active power regulation method based on optimal dynamic droop coefficient, comprising the following steps:

[0006] Step 1: Directly controlling massive DPVs will cause huge optimization dimensions and severe computing burden. Based on the business needs of fast active power regulation, we select adjustable capacity and response time as clustering features and apply the Uk-means algorithm to cluster massive DPVs.

[0007] Step 2: In order to accurately and safely meet the regulation tasks issued by the balancing agency, a frequency deviation-optimal droop coefficient model considering the regulation performance of the DPVs cluster and the active power transmission loss is constructed from the perspective of power flow optimization;

[0008] Step 3: Considering the high efficiency of graph neural networks in solving power flow related problems, and GAT can give greater weight to important features in neighbor information by introducing the attention mechanism, and has stronger expression performance, GAT is used to quickly solve the optimal droop coefficient adjustment strategy of DPVs under various frequency deviations in advance.

[0009] Furthermore, step 1.1. establishes the clustering characteristics of massive distributed photovoltaics.

[0010] In view of the business needs of fast active power regulation, the adjustable capacity of DPVs is selected from the perspective of the active power adjustable margin and rapidity of regulation of DPVs. and response time T dpv，t As clustering features, P dpv，0 Indicates the initial active power output value of distributed photovoltaics,

[0011] Step 1.2. Apply the Uk-means algorithm to cluster massive distributed photovoltaics.

[0012] (1) Input the clustering feature data X of m distributed photovoltaics under a bus line = {x1, x2, .., x j , .., x m}, In addition, due to the difference in the order of magnitude of the characteristic data, the range method is used to normalize the data.

[0013]

[0014] (2) Given the deviation threshold ε>0 for cluster center update, the maximum number of iterations k max And the maximum number of clusters Set the initial value of the number of iterations k = 0 and the initial value of the number of clusters respectively Initial value of cluster center Initial value of the probability that the data belongs to cluster I and the initial value λ of the learning parameter (0) =μ (0) =1,

[0015] (3) Calculate data according to formula (2) Whether it belongs to cluster i,

[0016]

[0017] (4) Update the learning parameter λ according to formula (3) (k+1) ,

[0018]

[0019] (5) Update the data attribution probability according to formula (4)

[0020]

[0021] (6) Update the learning parameter μ through formula (5) (k+1) ,

[0022]

[0023] (7) Update the number of clusters according to formula (6) And adjust by equation (7) and equation (8) respectively and If k ≥ k max and Adjust μ (k+1) =0,

[0024]

[0025] (8) Update the cluster center according to formula (8) If the maximum value of the updated cluster center is less than the cluster center deviation threshold And the updated number of clusters is less than the given maximum number of clusters The final clustering result is obtained, otherwise k=k+1, and steps (3)-(8) are repeated.

[0026] Furthermore, in step 2, based on the clustered DPVs, in order to accurately and safely meet the regulation tasks issued by the balancing mechanism, a frequency deviation-optimal droop coefficient model considering the regulation performance of the DPVs cluster and the active power transmission loss is constructed from the perspective of power flow optimization, as follows:

[0027] Step 2.1. For a power grid with n buses, establish a comprehensive optimization objective function:

[0028]

[0029] Among them, the decision variable is the droop coefficient K of the DPVs cluster s，i，t , is the number of distributed photovoltaic clusters at bus s at time t, γ s，i，t To adjust the performance index, the adjustable capacity of the cluster and response time Decide, represents the change in active power output by DPV cluster i at bus S at time t, and They represent the voltage vectors at bus r and bus s at time t, respectively. sr and X sr Respectively represent the resistance and reactance between busbars s and r, |·| represents the vector modulus, α1 and α2 are weight coefficients,

[0030] Step 2.2. For the above optimization model, the corresponding constraints are:

[0031]

[0032]

[0033] Among them, formula (10) is the droop constraint, K s，i，t They represent the upper and lower bounds of the droop coefficient adjustment, respectively. Equations (11)-(13) are the operating constraints of the distributed photovoltaic cluster. is the active power output value of DPV cluster i at bus S at time t, represents the initial output active power of DPV cluster i at bus S, f t is the system frequency at time t, fd is the frequency regulation dead zone, f N is the nominal frequency of the system, is the rated active power value of cluster i at bus S, which is obtained by summing the rated active power values ​​of distributed photovoltaics belonging to cluster i, P j，N is the rated active power value of distributed photovoltaic j, is the upper limit of active power output of DPV cluster i at bus S at time t, is the reactive power output value of DPV cluster i at bus S at time t, ρ CLU，N is the power factor value of the cluster, equations (14) and (15) are the power flow constraints, are the active power and reactive power of the load at bus S at time t, U s，t , U r，t is the voltage value at bus s, r at time t, G sr , B sr Respectively represent the conductance and susceptance between busbars s and r, θ sr，t =θ s，t -θ r，t is the phase angle difference between buses s and r at time t, and equation (16) is the bus voltage constraint. and U are the upper and lower limits of the bus voltage amplitude, equations (17) and (18) are the power balance constraints, Indicates the active power value of the root node interacting with the upper grid, that is, the regulation demand issued by the balancing mechanism The corresponding active power value is changed from the initial value and change value Decide.

[0034] Furthermore, in step 3, considering the high efficiency of graph neural networks in solving power flow related problems, GAT can give greater weight to important features in neighbor information by introducing the attention mechanism, and has stronger expression performance. GAT is used to quickly solve the droop coefficient optimization model under various frequency deviation conditions in advance, and the optimal droop coefficient adjustment strategy of DPVs is obtained, as follows:

[0035] Introduce a node feature h = {h1, h2, ..., h s , ..., h n}, h s ∈R f and connection relationship The grid information is described by a graph, where n and f represent the number and feature dimension of buses in the grid, respectively. The initial node feature

[0036]

[0037] Contains the active power and reactive power of the load, the upper and lower bounds of the adjustable droop coefficient of the cluster and the corresponding regulation performance indicators, is a binary matrix. When the busbars are directly connected, the matrix element is 1, otherwise it is 0.

[0038] Through the graph attention layer, the input feature h s Transformed into high-level feature h′ s , h′ s ∈R f′ The conversion process is as follows: First, in order to ensure that GAT has sufficient expression performance, a learnable linear transformation W is introduced, W∈R f′×2f ; Then, apply the dynamic masked self-attention strategy a, a∈R f′ Get the attention coefficient e between nodes sr , calculated by the following formula

[0039]

[0040] Among them, e sr Indicates the importance of the feature of node r to the bus S node, a is based on The attention coefficient is calculated only for the neighbors of the bus S node. LeakyReLU is a nonlinear activation function. represents transposition, || represents the connection operation,

[0041] Apply the softmax function to normalize the attention coefficient:

[0042]

[0043] Among them, n s represents the set of all neighbor nodes of s,

[0044] Expanding the above formula, the attention coefficient based on the attention mechanism is expressed as:

[0045]

[0046] Then, each node linearly combines the features of its neighbors according to the obtained attention coefficient, and completes the update of the node features through a nonlinear activation function σ, as shown in the following formula:

[0047]

[0048] Since the multi-head attention mechanism helps stabilize the learning process of the self-attention mechanism, D independent attention mechanisms are set according to formula (22), and these features are averaged to finally obtain the following graph attention network output feature representation:

[0049]

[0050] in, represents the normalized attention coefficient calculated by the dth attention mechanism, W is the corresponding weight matrix for linear transformation, and then the calculation results of all individual attention mechanisms are averaged. Therefore, the output feature dimension of each node in the final graph attention layer is f′.

[0051] Finally, the constructed graph attention network learns the mapping relationship between system operation status, grid topology and optimal droop coefficient, and pre-calculates the optimal droop coefficient adjustment strategy of distributed photovoltaic under any frequency deviation. s，i，t After that, the power-frequency relationship Realize DPVs active power output regulation.

[0052] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the DPVs fast active power regulation method based on the optimal dynamic droop coefficient is implemented.

[0053] A computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implements the DPVs fast active power regulation method based on the optimal dynamic droop coefficient

[0054] Compared with the prior art, the advantages of the present invention are as follows:

[0055] The present invention takes into account that directly regulating a large number of distributed photovoltaics will cause huge optimization dimensions and serious computational burdens. Starting from the needs of fast active power regulation services, the adjustable capacity and response speed of distributed photovoltaics are selected as clustering features, and the Uk-means algorithm is applied to achieve clustering of massive distributed photovoltaics, which greatly reduces the optimization dimension and improves the computational efficiency. Different from the unsafe and inaccurate power regulation caused by usually ignoring the power flow constraints in the prior art, the present invention considers the influence of network power flow in the process of designing the droop coefficient, see formulas (14)-(18), and considers the power flow constraints in the process of establishing the frequency deviation-optimal droop coefficient model, which can not only ensure the accurate response to the issued regulation instructions, but also ensure the bus voltage safety during the response process. Furthermore, the present invention realizes the efficient solution of the optimal droop coefficient regulation strategy of DPVs through the GAT method. GAT can aggregate information according to the importance of neighbor features in the topological space, and is more advanced and intelligent than the existing data-driven technology in solving optimization problems related to power flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1It is a flow chart of a DPVs fast active power regulation method based on an optimal dynamic droop coefficient provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to deepen the understanding of the present invention, the present embodiment is described in detail below with reference to the accompanying drawings.

[0058] Example: Figure 1 As shown, the purpose of the present invention is to provide a DPVs fast active power regulation method based on the optimal dynamic droop coefficient. In order to avoid the dimensionality disaster and heavy computational burden problems caused by directly regulating massive distributed photovoltaics, the present invention implements clustering of distributed photovoltaics based on the Uk-means algorithm. In order to accurately and safely achieve the active power regulation requirements of massive distributed photovoltaics specified by the balancing mechanism, based on the clustering results of distributed photovoltaics, from the perspective of power flow optimization, the present invention constructs a frequency deviation-optimal droop coefficient model that takes into account the active power regulation performance and transmission loss of DPVs clusters, and quickly solves through GAT, pre-calculates the optimal droop coefficient regulation strategy of distributed photovoltaics under various frequency deviations, ensures active response when frequency events occur, and realizes the output regulation of DPVs active power according to the power-frequency relationship.

[0059] The invention discloses a DPVs fast active power regulation method based on an optimal dynamic droop coefficient, comprising the following steps:

[0060] Step 1: In order to realize the clustering of massive distributed photovoltaics, the adjustable capacity and response time are selected as clustering features, and the Uk-means algorithm is applied to cluster the massive DPVs;

[0061] (1) Input the clustering feature data X of m distributed photovoltaics under a bus line = {x1, x2, .., x j , .., x m}, In addition, due to the difference in the order of magnitude of the characteristic data, the range method is used to normalize the data.

[0062]

[0063] (2) Given the deviation threshold ε>0 for cluster center update, the maximum number of iterations k max And the maximum number of clusters Set the initial value of the number of iterations k = 0 and the initial value of the number of clusters respectively Initial value of cluster center Initial value of the probability that the data belongs to cluster I and the initial value λ of the learning parameter (0) =μ (0) =1,

[0064] (3) Calculate data according to formula (2) Whether it belongs to cluster i,

[0065]

[0066] (4) Update the learning parameter λ according to formula (3) (k+1) ,

[0067]

[0068] (5) Update the data attribution probability according to formula (4)

[0069]

[0070] (6) Update the learning parameter μ through formula (5) (k+1) ,

[0071]

[0072] (7) Update the number of clusters according to formula (6) And adjust by equation (7) and equation (8) respectively and If k ≥ k max and Adjust μ (k+1) =0,

[0073]

[0074] (8) Update the cluster center according to formula (8) If the maximum value of the updated cluster center is less than the cluster center deviation threshold And the updated number of clusters is less than the given maximum number of clusters The final clustering result is obtained, otherwise k=k+1, and steps (3)-(8) are repeated.

[0075] Step 2: Based on the clustered DPVs, in order to accurately and safely meet the regulation tasks issued by the balancing agency, a frequency deviation-optimal droop coefficient model considering the regulation performance of the DPVs cluster and the active power transmission loss is constructed from the perspective of power flow optimization:

[0076] Step 2.1. For a power grid with n buses, establish a comprehensive optimization objective function:

[0077]

[0078] Among them, the decision variable is the droop coefficient K of the DPVs cluster s，i，t , is the number of distributed photovoltaic clusters at bus s at time t, γ s，i，t To adjust the performance index, the adjustable capacity of the cluster and response time Decide, represents the change in active power output by DPV cluster i at bus S at time t, and They represent the voltage vectors at bus r and bus s at time t, respectively. sr and X sr Respectively represent the resistance and reactance between busbars s and r, |·| represents the vector modulus, α1 and α2 are weight coefficients,

[0079] Step 2.2. For the above optimization model, the corresponding constraints are:

[0080]

[0081]

[0082] Among them, formula (10) is the droop constraint, K s，i，t They represent the upper and lower bounds of the droop coefficient adjustment, respectively. Equations (11)-(13) are the operating constraints of the distributed photovoltaic cluster. is the active power output value of DPV cluster i at bus S at time t, represents the initial output active power of DPV cluster i at bus S, f t is the system frequency at time t, f d is the frequency regulation dead zone, f N is the nominal frequency of the system, is the rated active power value of cluster i at bus S, which is obtained by summing the rated active power values ​​of distributed photovoltaics belonging to cluster i, P j，N is the rated active power value of distributed photovoltaic j, is the upper limit of active power output of DPV cluster i at bus S at time t, is the reactive power output value of DPV cluster i at bus S at time t, ρ CLU，N is the power factor value of the cluster, equations (14) and (15) are the power flow constraints, are the active power and reactive power of the load at bus S at time t, U s，t , U r，t is the voltage value at bus S,r at time t, G sr , B sr Respectively represent the conductance and susceptance between busbars s and r, θsr,t =θ s,t -θ r,t is the phase difference between buses S and r at time t, and equation (16) is the bus voltage constraint. and U are the upper and lower limits of the bus voltage amplitude, equations (17) and (18) are power balance constraints, Indicates the active power value of the root node interacting with the upper grid, that is, the regulation demand issued by the balancing mechanism The corresponding active power value is changed from the initial value and change value Decide.

[0083] Step 3: Considering the high efficiency of graph neural networks in solving power flow related problems, GAT can give greater weight to important features in neighbor information by introducing the attention mechanism, and has stronger expression performance. GAT is used to quickly solve the droop coefficient optimization model under various frequency deviation conditions in advance, and the optimal droop coefficient adjustment strategy of DPVs is obtained;

[0084] Introduce a node feature h = {h1,h2,…,h s ,…,h n}, h s ∈R f and connection relationship The grid information is described by a graph, where n and f represent the number and feature dimension of buses in the grid, respectively. The initial node feature

[0085]

[0086] Contains the active power and reactive power of the load, the upper and lower bounds of the adjustable droop coefficient of the cluster and the corresponding regulation performance indicators, is a binary matrix. When the busbars are directly connected, the matrix element is 1, otherwise it is 0.

[0087] (2) Through the graph attention layer, the input feature h s Transformed into high-level feature h′ s , h′∈R f′ The conversion process is as follows: First, in order to ensure that GAT has sufficient expression performance, a learnable linear transformation W is introduced, W∈R f′×2f ; Then, apply the dynamic masked self-attention strategy a, a∈R f′ Get the attention coefficient e between nodes sr , calculated by the following formula

[0088]

[0089] Among them, e srIndicates the importance of the feature of node r to the bus S node, a is based on The attention coefficient is calculated only for the neighbors of the bus S node. LeakyReLU is a nonlinear activation function. represents transposition, || represents the connection operation,

[0090] Furthermore, in order to avoid the adverse effects of coefficients of different orders of magnitude between nodes on feature aggregation, the softmax function is applied to normalize the attention coefficients:

[0091]

[0092] Among them, n s represents the set of all neighbor nodes of S,

[0093] Expanding the above formula, the attention coefficient based on the attention mechanism is expressed as:

[0094]

[0095] Then, each node linearly combines the features of its neighbors according to the obtained attention coefficient, and completes the update of the node features through a nonlinear activation function σ, as shown in the following formula:

[0096]

[0097] Since the multi-head attention mechanism helps stabilize the learning process of the self-attention mechanism, D independent attention mechanisms are set according to formula (22), and these features are averaged to finally obtain the following graph attention network output feature representation:

[0098]

[0099] in, represents the normalized attention coefficient calculated by the dth attention mechanism, W is the corresponding weight matrix for linear transformation, and then the calculation results of all individual attention mechanisms are averaged. Therefore, the output feature dimension of each node in the final graph attention layer is f′.

[0100] Finally, the constructed graph attention network learns the mapping relationship between system operation status, grid topology and optimal droop coefficient, and pre-calculates the optimal droop coefficient adjustment strategy of distributed photovoltaic under any frequency deviation. s，i，t After that, the power-frequency relationship Realize DPVs active power output regulation.

[0101] (3) In order to verify the effectiveness of GAT, the mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) performance indicators were used for testing.

[0102]

[0103] Among them, n test Indicates the number of samples in the test set, n o is the output data dimension of GAT, is the sample label, y n，i is the output value of GAT.

[0104] It should be noted that the above embodiments are not intended to limit the protection scope of the present invention, and equivalent changes or substitutions made on the basis of the above technical solutions all fall within the protection scope of the claims of the present invention.

Claims

1. A DPVs fast active power regulation method based on an optimal dynamic droop coefficient, characterized in that: The method comprises the following steps: Step 1: Directly controlling massive DPVs will cause huge optimization dimensions and severe computing burden. Based on the business needs of fast active power regulation, we select adjustable capacity and response time as clustering features and apply the Uk-means algorithm to cluster massive DPVs. Step 2: Construct a frequency deviation-optimal droop coefficient model considering the regulation performance of DPVs cluster and active power transmission loss; Step 3: Use GAT to quickly solve the optimal droop coefficient adjustment strategy of DPVs under various frequency deviation conditions in advance; Among them, in step 1, the Uk-means algorithm is used to cluster the massive DPVs, as follows: Step 1.

1. Establish the clustering characteristics of massive distributed photovoltaics. In view of the business needs of fast active power regulation, the adjustable capacity of DPVs is selected from the perspective of the active power adjustable margin and rapidity of regulation of DPVs. and response time T dpv，t As clustering features, P dpv，0 Indicates the initial active power output value of distributed photovoltaics, Step 1.

2. Apply the Uk-means algorithm to cluster massive distributed photovoltaics. (1) Input the clustering feature data X of m distributed photovoltaics under a bus line = {x1, x2, .., x j , .., x m }, The data were normalized using the range method. (2) Given the deviation threshold ε>0 for cluster center update, the maximum number of iterations k max And the maximum number of clusters Set the initial value of the number of iterations k = 0 and the initial value of the number of clusters respectively Initial value of cluster center Initial value of the probability that the data belongs to cluster I and the initial value λ of the learning parameter (0) =μ (0) =1, (3) Calculate data according to formula (2) Whether it belongs to cluster i, (4) Update the learning parameter λ according to formula (3) (k+1) , (5) Update the data attribution probability according to formula (4) (6) Update the learning parameter μ through formula (5) (k+1) , (7) Update the number of clusters according to formula (6) And adjust by equation (7) and equation (8) respectively and If k ≥ k max and Adjust μ (k+1) =0, (8) Update the cluster center according to formula (8) If the maximum value of the updated cluster center is less than the cluster center deviation threshold And the updated number of clusters is less than the given maximum number of clusters The final clustering result is obtained, otherwise k=k+1, and steps (3)-(8) are repeated.

2. The DPVs fast active power regulation method based on the optimal dynamic droop coefficient according to claim 1 is characterized in that: Step 2: Based on the clustered DPVs, a frequency deviation-optimal droop coefficient model is constructed that takes into account the regulation performance of the DPVs cluster and the active power transmission loss. The details are as follows: Step 2.

1. For a power grid with n buses, establish a comprehensive optimization objective function: Among them, the decision variable is the droop coefficient K of the DPVs cluster s，i，t , is the number of distributed photovoltaic clusters at bus s at time t, γ s，i，t To adjust the performance index, the adjustable capacity of the cluster and response time Decide, represents the change in active power output by DPV cluster i at bus s at time t, and They represent the voltage vectors at bus r and bus s at time t, respectively. sr and X sr Respectively represent the resistance and reactance between busbars s and r, |·| represents the vector modulus, α1 and α2 are weight coefficients, Step 2.

2. For the above optimization model, the corresponding constraints are: Among them, formula (10) is the droop constraint, K s，i，t They represent the upper and lower bounds of the droop coefficient adjustment, respectively. Equations (11)-(13) are the operating constraints of the distributed photovoltaic cluster. is the active power output value of DPV cluster i at bus s at time t, represents the initial output active power of DPV cluster i at bus s, f t is the system frequency at time t, f d is the frequency regulation dead zone, f N is the nominal frequency of the system, is the rated active power value of cluster i at bus s, which is obtained by summing the rated active power values ​​of distributed photovoltaics belonging to cluster i, P j，N is the rated active power value of distributed photovoltaic j, is the upper limit of active power output of DPV cluster i at bus s at time t, is the reactive power output value of DPV cluster i at bus s at time t, ρ CLU，N is the power factor value of the cluster, equations (14) and (15) are the power flow constraints, are respectively the active power and reactive power of the load at bus s at time t, U s，t , U r，t is the voltage value at bus s, r at time t, G sr , B sr Respectively represent the conductance and susceptance between busbars s and r, θ sr,t =θ s,t -θ r,t is the phase difference between buses s and r at time t, and equation (16) is the bus voltage constraint. and U are the upper and lower limits of the bus voltage amplitude, equations (17) and (18) are power balance constraints, Indicates the active power value of the root node interacting with the upper grid, that is, the regulation demand issued by the balancing agency The corresponding active power value is changed from the initial value and change value Decide.

3. The DPVs fast active power regulation method based on the optimal dynamic droop coefficient according to claim 1 is characterized in that: In step 3, GAT is used to quickly solve the droop coefficient optimization model under various frequency deviation conditions in advance to obtain the optimal droop coefficient adjustment strategy for DPVs, as follows: Introduce a node feature h = {h1,h2,…,h s ,…,h n }, h s ∈R f and connection relationship The grid information is described by a graph, where n and f represent the number and feature dimension of buses in the grid, respectively. The initial node feature Contains the active power and reactive power of the load, the upper and lower bounds of the adjustable droop coefficient of the cluster and the corresponding regulation performance indicators, is a binary matrix. When the busbars are directly connected, the matrix element is 1, otherwise it is 0. Through the graph attention layer, the input feature h s Transformed into high-level feature h′ s , h′ s ∈R f′ The conversion process is as follows: First, in order to ensure that GAT has sufficient expression performance, a learnable linear transformation W is introduced, W∈R f′×2f ; Then, apply the dynamic masked self-attention strategy a, a∈R f′ Get the attention coefficient e between nodes sr , calculated by the following formula Among them, e sr Indicates the importance of the feature of node r to the bus node s, a is based on The attention coefficient is calculated only for the neighbors of the bus s node. LeakyReLU is a nonlinear activation function. represents transposition, || represents a connection operation, Apply the softmax function to normalize the attention coefficient: in, represents the set of all neighbor nodes of s, Then, each node linearly combines the features of its neighbors according to the obtained attention coefficient, and completes the update of the node features through a nonlinear activation function σ, as shown in the following formula: Since the multi-head attention mechanism helps stabilize the learning process of the self-attention mechanism, D independent attention mechanisms are set according to formula (22), and these features are averaged to finally obtain the following graph attention network output feature representation: in, represents the normalized attention coefficient calculated by the dth attention mechanism, W is the corresponding weight matrix for linear transformation, and then the calculation results of all individual attention mechanisms are averaged. Therefore, the output feature dimension of each node in the final graph attention layer is f′, Finally, the mapping relationship between system operation status, grid topology and optimal droop coefficient is learned through the constructed graph attention network, and the optimal droop coefficient adjustment strategy of distributed photovoltaic under any frequency fluctuation range is pre-calculated. s，i，t Then, through the power-frequency relationship Realize DPVs active power output regulation.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the DPVs fast active power regulation method based on the optimal dynamic droop coefficient as described in any one of claims 1 to 3 above is implemented.

5. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instruction is executed by the processor, the DPVs fast active power regulation method based on the optimal dynamic droop coefficient as described in any one of claims 1-3 is implemented.

Images